Algorithms for Data Migration

Authors:
E. Anderson;J. Hall;J. Hartline;M. Hobbes;A. Karlin;J. Saia;R. Swaminathan;J. Wilkes
Affiliations:
Hewlett–Packard Laboratories, 94304, Palo Alto, CA, USA;University of Washington, Department of Computer Science, 98195, Seattle, WA, USA;Northwestern University, Department of Electrical Engineering and Computer Science, 60208, Evanston, IL, USA;Deakin University, School of Engineering and Information Technology, 3217, Geelong, VIC, Australia;University of Washington, Department of Computer Science, 98195, Seattle, WA, USA;University of New Mexico, Department of Computer Science, 87131, Albuquerque, NM, USA;Hewlett–Packard Laboratories, 94304, Palo Alto, CA, USA;Hewlett–Packard Laboratories, 94304, Palo Alto, CA, USA
Venue:
Algorithmica
Year:
2010

Citing 0
Cited 3

Bin repacking scheduling in virtualized datacenters

CP'11 Proceedings of the 17th international conference on Principles and practice of constraint programming
An energy aware framework for virtual machine placement in cloud federated data centres

Proceedings of the 3rd International Conference on Future Energy Systems: Where Energy, Computing and Communication Meet
Editorial: Data migration: A theoretical perspective

Data & Knowledge Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

The data migration problem is the problem of computing a plan for moving data objects stored on devices in a network from one configuration to another. Load balancing or changing usage patterns might necessitate such a rearrangement of data. In this paper, we consider the case where the objects are fixed-size and the network is complete. Our results are both theoretical and empirical. Our main theoretical results are (1) a polynomial time algorithm for finding a near-optimal migration plan in the presence of space constraints when a certain number of additional nodes is available as temporary storage, and (2) a 3/2-approximation algorithm for the case where data must be migrated directly to its destination. We also run extensive experiments on several algorithms for various data migration problems and show that empirically, many algorithms perform better in practice than their theoretical bounds suggest. We conclude that many of the algorithms we present are both practical and effective for data migration.